© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9523
    Prev
    Next
    INDEX
    Explanations

    terms related to blood cell types, particularly studying their properties and functions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ReusableCell
    -0.78
    Yann
    -0.75
    неопр
    -0.73
     Yann
    -0.71
    jspx
    -0.68
    pexpr
    -0.68
     Eins
    -0.65
    r
    -0.64
    StrictEqual
    -0.63
    </b>
    -0.62
    POSITIVE LOGITS
     oocytes
    1.42
    ocyte
    1.25
    ocytes
    1.07
     monocytes
    0.92
    cyte
    0.88
     Voigt
    0.88
     tartalomajánló
    0.82
     Henley
    0.80
     pleaſure
    0.79
    graduates
    0.78
    Activations Density 0.013%

    No Known Activations